NVIDIA NemoClaw CKG
Level CRemoteNVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.
Installation
MCP client config (paste into mcp.json)
{
"mcpServers": {
"ckg-nvidia-nemoclaw": {
"url": "https://ckg-nvidia-nemoclaw.onrender.com/mcp"
}
}
}Agent install prompt
Copy and paste into Cursor / Claude / other agents to install this MCP for you
Please read this MCP repository and install it into my current environment:
https://github.com/Yarmoluk/ckg-nvidia-nemoclaw
Known working client config (can write into mcp.json):
{
"mcpServers": {
"ckg-nvidia-nemoclaw": {
"url": "https://ckg-nvidia-nemoclaw.onrender.com/mcp"
}
}
}
Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.
Related servers
NVIDIA AI CKGNVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenSalesforce AgentForce CKGSalesforce AgentForce knowledge graph — 40 nodes, Einstein Trust Layer, 11x fewemempalaceThe best-benchmarked open-source AI memory system. And it's free.private-gptComplete API layer for private AI applications on local models: RAG, skills, toocodebase-memory-mcpLocal code intelligence for developers and AI agents. Connect code, docs and infcontext-modeFree, local plugin that keeps tool output out of your coding agent's context win